Upload model

README.md

@@ -0,0 +1,28 @@
+---
+language:
+- en
+- ja
+---
+
+# Pythia 410M fine-tuned on Light Novels
+
+This model was fine-tuned on light and web novels. This model was trained for translation, but can do generation too.
+
+This model is a test of using monolingual data to improve translation as well as improving translation by adding similar sentence pairs to prompts.
+
+
+## English generation
+To generate English text with this model, start your prompt with `<|gen_en|>`.
+
+
+## Japanese generation
+To generate Japanese text with this model, start your prompt with `<|gen_ja|>`.
+
+
+## Japanese to English translation
+To translate, format your prompt as such
+```
+<|tl_ja|>JAPANESE EXAMPLE SENTENCE 1<|tl_en|>ENGLISH EXAMPLE SENTENCE 1<|tl_end|>
+<|tl_ja|>JAPANESE EXAMPLE SENTENCE 2<|tl_en|>ENGLISH EXAMPLE SENTENCE 2<|tl_end|>
+<|tl_ja|>JAPANESE SENTENCE TO TRANSLATE<|tl_en|>
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "EleutherAI/pythia-350m-deduped",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50282
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7131d1ea123bf4246335496fe8d4cbcaac4e36772e53cab4bc6a0247e9d8fc
+size 1721942141

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "EleutherAI/pythia-350m",
+  "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}